Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Added exception handling to code quality transform #746

Open
wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

Added exception handling to code quality transform #746

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 37 additions & 15 deletions transforms/code/code_quality/python/src/code_quality_transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,25 +223,45 @@ def transform(self, table: pa.Table, file_name: str = None) -> tuple[list[pa.Tab

contents = table.column(self.code_quality["contents_column_name"]).to_pylist()
languages = table.column(self.code_quality["language_column_name"]).to_pylist()
document_id = table.column("document_id").to_pylist()

failed_doc_ids = []
# loop over rows and compute filter stats
for i, c in enumerate(contents):
# compute lines statistics
stats = calculate_line_stats(c)
line_mean_values.append(stats["line_mean"])
line_max_values.append(stats["line_max"])
no_lines_values.append(stats["num_lines"])
avg_longest_lines_values.append(stats["avg_longest_lines"])

alphanum_frac_values.append(calculate_alpha_stats(c)["alphanum_frac"])
char_token_ratio_values.append(calculate_char_token_ratio(c, self.tokenizer)["char_token_ratio"])

is_autogenerated_values.append(is_autogenerated(c))
is_config_or_test_values.append(is_config_or_test(c))
has_no_keywords_values.append(has_no_keywords(c, languages[i]))
has_few_assignments_values.append(has_few_assignments(c, languages[i]))
is_xml_values.append(is_xml(c, languages[i]))
is_html_values.append(is_html(c, languages[i]))
try:
stats = calculate_line_stats(c)
line_mean_values.append(stats["line_mean"])
line_max_values.append(stats["line_max"])
no_lines_values.append(stats["num_lines"])
avg_longest_lines_values.append(stats["avg_longest_lines"])

alphanum_frac_values.append(calculate_alpha_stats(c)["alphanum_frac"])
char_token_ratio_values.append(calculate_char_token_ratio(c, self.tokenizer)["char_token_ratio"])

is_autogenerated_values.append(is_autogenerated(c))
is_config_or_test_values.append(is_config_or_test(c))
has_no_keywords_values.append(has_no_keywords(c, languages[i]))
has_few_assignments_values.append(has_few_assignments(c, languages[i]))
is_xml_values.append(is_xml(c, languages[i]))
is_html_values.append(is_html(c, languages[i]))
except Exception as e:
failed_doc_ids.append(document_id[i])
line_mean_values.append(0)
line_max_values.append(0)
no_lines_values.append(0)
avg_longest_lines_values.append(0)

alphanum_frac_values.append(0)
char_token_ratio_values.append(0)

is_autogenerated_values.append(False)
is_config_or_test_values.append(False)
has_no_keywords_values.append(False)
has_few_assignments_values.append(True)
is_xml_values.append(False)
is_html_values.append(False)


table = TransformUtils.add_column(table=table, name="line_mean", content=line_mean_values)
table = TransformUtils.add_column(table=table, name="line_max", content=line_max_values)
Expand All @@ -256,6 +276,8 @@ def transform(self, table: pa.Table, file_name: str = None) -> tuple[list[pa.Tab
table = TransformUtils.add_column(table=table, name="is_xml", content=is_xml_values)
table = TransformUtils.add_column(table=table, name="is_html", content=is_html_values)

if len(failed_doc_ids > 0):
print(f"Failed docs: {failed_doc_ids} in {file_name}")
return [table], {}


Expand Down
Loading